pdfreader.java

一个java操作pdf文件的开发包,很好用的.

/*
 * $Id: PdfReader.java,v 1.21 2002/11/19 08:33:38 blowagie Exp $
 * $Name:  $
 *
 * Copyright 2001, 2002 Paulo Soares
 *
 * The contents of this file are subject to the Mozilla Public License Version 1.1
 * (the "License"); you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at http://www.mozilla.org/MPL/
 *
 * Software distributed under the License is distributed on an "AS IS" basis,
 * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
 * for the specific language governing rights and limitations under the License.
 *
 * The Original Code is 'iText, a free JAVA-PDF library'.
 *
 * The Initial Developer of the Original Code is Bruno Lowagie. Portions created by
 * the Initial Developer are Copyright (C) 1999, 2000, 2001, 2002 by Bruno Lowagie.
 * All Rights Reserved.
 * Co-Developer of the code is Paulo Soares. Portions created by the Co-Developer
 * are Copyright (C) 2000, 2001, 2002 by Paulo Soares. All Rights Reserved.
 *
 * Contributor(s): all the names of the contributors are added in the source code
 * where applicable.
 *
 * Alternatively, the contents of this file may be used under the terms of the
 * LGPL license (the "GNU LIBRARY GENERAL PUBLIC LICENSE"), in which case the
 * provisions of LGPL are applicable instead of those above.  If you wish to
 * allow use of your version of this file only under the terms of the LGPL
 * License and not to allow others to use your version of this file under
 * the MPL, indicate your decision by deleting the provisions above and
 * replace them with the notice and other provisions required by the LGPL.
 * If you do not delete the provisions above, a recipient may use your version
 * of this file under either the MPL or the GNU LIBRARY GENERAL PUBLIC LICENSE.
 *
 * This library is free software; you can redistribute it and/or modify it
 * under the terms of the MPL as stated above or under the terms of the GNU
 * Library General Public License as published by the Free Software Foundation;
 * either version 2 of the License, or any later version.
 *
 * This library is distributed in the hope that it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
 * FOR A PARTICULAR PURPOSE. See the GNU Library general Public License for more
 * details.
 *
 * If you didn't download this code from the following link, you should check if
 * you aren't using an obsolete version:
 * http://www.lowagie.com/iText/
 */

package com.lowagie.text.pdf;

import java.io.*;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.Iterator;
import com.lowagie.text.Rectangle;
import java.util.zip.InflaterInputStream;
import java.util.zip.ZipInputStream;
/** Reads a PDF document and prepares it to import pages to our
 * document. This class is not mutable and is thread safe; this means that
 * a single instance can serve as many output documents as needed and can even be static.
 * @author Paulo Soares ([e-mail])
 */
public class PdfReader {

    static final PdfName pageInhCandidates[] = {
        PdfName.MEDIABOX, PdfName.ROTATE, PdfName.RESOURCES, PdfName.CROPBOX};

    protected PRTokeniser tokens;
    protected int xref[];
    protected PdfObject xrefObj[];
    protected PdfDictionary trailer;
    protected PdfDictionary pages[];
    protected PdfDictionary catalog;
    protected PRIndirectReference pageRefs[];
    protected PRAcroForm acroForm = null;
    protected ArrayList pageInh;
    protected int pagesCount;
    protected boolean encrypted = false;
    protected boolean rebuilt = false;
    
    /** Reads and parses a PDF document.
     * @param filename the file name of the document
     * @throws IOException on error
     */    
    public PdfReader(String filename) throws IOException {
        tokens = new PRTokeniser(filename);
        readPdf();
    }
    
    /** Reads and parses a PDF document.
     * @param pdfIn the byte array with the document
     * @throws IOException on error
     */    
    public PdfReader(byte pdfIn[]) throws IOException {
        tokens = new PRTokeniser(pdfIn);
        readPdf();
    }
    
    public RandomAccessFileOrArray getSafeFile() {
        return tokens.getSafeFile();
    }
    
    protected PdfReaderInstance getPdfReaderInstance(PdfWriter writer) {
        return new PdfReaderInstance(this, writer, xrefObj, pages);
    }
    
    /** Gets the number of pages in the document.
     * @return the number of pages in the document
     */    
    public int getNumberOfPages() {
        return pages.length;
    }
    
    /**
     * Returns the document's catalog
     */
    public PdfDictionary getCatalog() {
        return catalog;
    }

    /**
     * Returns the document's acroform, if it has one
     */
     public PRAcroForm getAcroForm() {
	    return acroForm;
     }
    /**
     * Gets the page rotation. This value can be 0, 90, 180 or 270.
     * @param index the page number. The first page is 1
     * @return the page rotation
     */    
    public int getPageRotation(int index) {
        PdfDictionary page = pages[index - 1];
        PdfNumber rotate = (PdfNumber)getPdfObject(page.get(PdfName.ROTATE));
        if (rotate == null)
            return 0;
        else
            return rotate.intValue();
    }
    
    /** Gets the page size, taking rotation into account. This
     * is a <CODE>Rectangle</CODE> with the value of the /MediaBox and the /Rotate key.
     * @param index the page number. The first page is 1
     * @return a <CODE>Rectangle</CODE>
     */    
    public Rectangle getPageSizeWithRotation(int index) {
        Rectangle rect = getPageSize(index);
        int rotation = getPageRotation(index);
        while (rotation > 0) {
            rect = rect.rotate();
            rotation -= 90;
        }
        return rect;
    }
    
    /** Gets the page size without taking rotation into account. This
     * is the value of the /MediaBox key.
     * @param index the page number. The first page is 1
     * @return the page size
     */    
    public Rectangle getPageSize(int index) {
        PdfDictionary page = pages[index - 1];
        PdfArray mediaBox = (PdfArray)getPdfObject(page.get(PdfName.MEDIABOX));
        return getNormalizedRectangle(mediaBox);
    }
    
    /** Gets the crop box without taking rotation into account. This
     * is the value of the /CropBox key. The crop box is the part
     * of the document to be displayed or printed. It usually is the same
     * as the media box but may be smaller.
     * @param index the page number. The first page is 1
     * @return the crop box
     */    
    public Rectangle getCropBox(int index) {
        PdfDictionary page = pages[index - 1];
        PdfArray cropBox = (PdfArray)getPdfObject(page.get(PdfName.CROPBOX));
        if (cropBox == null)
            return getPageSize(index);
        return getNormalizedRectangle(cropBox);
    }
    
    /** Returns the content of the document information dictionary as a <CODE>HashMap</CODE>
     * of <CODE>String</CODE>.
     * @return content of the document information dictionary
     */    
    public HashMap getInfo() {
        HashMap map = new HashMap();
        PdfDictionary info = (PdfDictionary)getPdfObject(trailer.get(PdfName.INFO));
        if (info == null)
            return map;
        for (Iterator it = info.getKeys().iterator(); it.hasNext();) {
            PdfName key = (PdfName)it.next();
            PdfObject obj = (PdfObject)getPdfObject(info.get(key));
            if (obj == null)
                continue;
            String value = obj.toString();
            switch (obj.type()) {
                case PdfObject.STRING: {
                    byte b[] = PdfEncodings.convertToBytes(value, null);
                    if (b.length >= 2 && b[0] == (byte)254 && b[1] == (byte)255)
                        value = PdfEncodings.convertToString(b, PdfObject.TEXT_UNICODE);
                    else
                        value = PdfEncodings.convertToString(b, PdfObject.ENCODING);
                    break;
                }
                case PdfObject.NAME: {
                    value = PdfName.decodeName(value);
                    break;
                }
            }
            map.put(PdfName.decodeName(key.toString()), value);
        }
        return map;
    }
    
    public static Rectangle getNormalizedRectangle(PdfArray box) {
        ArrayList rect = box.getArrayList();
        float llx = ((PdfNumber)rect.get(0)).floatValue();
        float lly = ((PdfNumber)rect.get(1)).floatValue();
        float urx = ((PdfNumber)rect.get(2)).floatValue();
        float ury = ((PdfNumber)rect.get(3)).floatValue();
        return new Rectangle(Math.min(llx, urx), Math.min(lly, ury),
            Math.max(llx, urx), Math.max(lly, ury));
    }
    
    protected void readPdf() throws IOException {
        try {
            tokens.checkPdfHeader();
            try {
                readXref();
            }
            catch (Exception e) {
                if (encrypted)
                    throw (IOException)e;
                try {
                    rebuilt = true;
                    rebuildXref();
                }
                catch (Exception ne) {
                    throw new IOException("Rebuild failed: " + ne.getMessage() + "; Original message: " + e.getMessage());
                }
            }
            readDocObj();
            readPages();
            PdfObject form = catalog.get(PdfName.ACROFORM);
            if (form != null) {
	      acroForm = new PRAcroForm(this);
	      acroForm.readAcroForm((PdfDictionary)getPdfObject(form));
            }
        }
        finally {
            try {
                tokens.close();
            }
            catch (Exception e) {
                // empty on purpose
            }
        }
    }

    public PdfObject getPdfObject(PdfObject obj) {
        if (obj == null)
            return null;
        if (obj.type() != PdfObject.INDIRECT)
            return obj;
        int idx = ((PRIndirectReference)obj).getNumber();
        obj = xrefObj[idx];
        if (obj == null)
            return PdfNull.PDFNULL;
        else
            return obj;
    }
    
    protected void pushPageAttributes(PdfDictionary nodePages) {
        PdfDictionary dic = new PdfDictionary();
        if (pageInh.size() != 0) {
            dic.putAll((PdfDictionary)pageInh.get(pageInh.size() - 1));
        }
        for (int k = 0; k < pageInhCandidates.length; ++k) {
            PdfObject obj = nodePages.get(pageInhCandidates[k]);
            if (obj != null)
                dic.put(pageInhCandidates[k], obj);
        }
        pageInh.add(dic);
    }

    protected void popPageAttributes() {
        pageInh.remove(pageInh.size() - 1);
    }
    
    protected void iteratePages(PdfDictionary page) throws IOException {
        PdfName type = (PdfName)getPdfObject(page.get(PdfName.TYPE));
        if (type.equals(PdfName.PAGE)) {
            PdfDictionary dic = (PdfDictionary)pageInh.get(pageInh.size() - 1);
            PdfName key;
            for (Iterator i = dic.getKeys().iterator(); i.hasNext();) {
                key = (PdfName)i.next();
                if (page.get(key) == null)
                    page.put(key, dic.get(key));
            }
            pages[pagesCount++] = page;
        }
        else {
            pushPageAttributes(page);
            PdfArray kidsPR = (PdfArray)getPdfObject(page.get(PdfName.KIDS));
            ArrayList kids = kidsPR.getArrayList();
            for (int k = 0; k < kids.size(); ++k){
                pageRefs[pagesCount] = (PRIndirectReference)kids.get(k);
                PdfDictionary kid = (PdfDictionary)getPdfObject(pageRefs[pagesCount]);
                iteratePages(kid);
            }
            popPageAttributes();
        }
    }
    
    protected void readPages() throws IOException {
        pageInh = new ArrayList();
        catalog = (PdfDictionary)getPdfObject(trailer.get(PdfName.ROOT));
        PdfDictionary rootPages = (PdfDictionary)getPdfObject(catalog.get(PdfName.PAGES));
        PdfNumber count = (PdfNumber)getPdfObject(rootPages.get(PdfName.COUNT));
        pages = new PdfDictionary[count.intValue()];
        pageRefs = new PRIndirectReference[pages.length];
        pagesCount = 0;
        iteratePages(rootPages);
        pageInh = null;
    }
    
    protected void readDocObj() throws IOException {
        ArrayList streams = new ArrayList();
        xrefObj = new PdfObject[xref.length];
        for (int k = 1; k < xrefObj.length; ++k) {
            int pos = xref[k];
            if (pos <= 0)
                continue;
            tokens.seek(pos);
            tokens.nextValidToken();
            if (tokens.getTokenType() != PRTokeniser.TK_NUMBER)
                tokens.throwError("Invalid object number.");
            int objNum = tokens.intValue();
            tokens.nextValidToken();
            if (tokens.getTokenType() != PRTokeniser.TK_NUMBER)
                tokens.throwError("Invalid generation number.");
            int objGen = tokens.intValue();
            tokens.nextValidToken();
            if (!tokens.getStringValue().equals("obj"))
                tokens.throwError("Token 'obj' expected.");
            PdfObject obj = readPRObject();
            xrefObj[k] = obj;
            if (obj.type() == PdfObject.STREAM)
                streams.add(obj);
        }
        for (int k = 0; k < streams.size(); ++k) {
            PRStream stream = (PRStream)streams.get(k);
            PdfObject length = getPdfObject(stream.get(PdfName.LENGTH));
            stream.setLength(((PdfNumber)length).intValue());
        }
    }
    
    protected void readXref() throws IOException {